English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Without human annotations, a typical Unsupervised Video Anomaly Detection(UVAD) method needs to train two models that generate pseudo labels for eachother. In previous work, the two models are closely entangled with each other,and it is not known how to upgrade their method without modifying theirtraining framework significantly. Second, previous work usually adopts fixedthresholding to obtain pseudo labels, however the user-specified threshold isnot reliable which inevitably introduces errors into the training process. Toalleviate these two problems, we propose a novel interleaved framework thatalternately trains a One-Class Classification (OCC) model and aWeakly-Supervised (WS) model for UVAD. The OCC or WS models in our method canbe easily replaced with other OCC or WS models, which facilitates our method toupgrade with the most recent developments in both fields. For handling thefixed thresholding problem, we break through the conventional cognitiveboundary and propose a weighted OCC model that can be trained on both normaland abnormal data. We also propose an adaptive mechanism for automaticallyfinding the optimal threshold for the WS model in a loose to strict manner.Experiments demonstrate that the proposed UVAD method outperforms previousapproaches.

Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection